{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0ee015fd",
   "metadata": {},
   "source": [
    "# PaddleOCR を SageMaker にデプロイする\n",
    "\n",
    "## 1. コンテナイメージを作成する\n",
    "\n",
    "ここにあるサンプルスクリプトを参考にして作成します。\n",
    "\n",
    "https://github.com/aws/amazon-sagemaker-examples/tree/master/advanced_functionality/multi_model_bring_your_own\n",
    "\n",
    "\n",
    "### 1.1 領域の確保\n",
    "\n",
    "まずコンテナイメージ作成に必要な領域をホームディレクトリに確保し、ここでビルドに必要なものを保存するようにします。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "b0987a7c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stopping docker: \u001b[60G[\u001b[0;32m  OK  \u001b[0;39m]\n",
      "Starting docker:\t.\u001b[60G[\u001b[0;32m  OK  \u001b[0;39m]\n"
     ]
    }
   ],
   "source": [
    "!sudo /etc/init.d/docker stop\n",
    "!mkdir /home/ec2-user/SageMaker/docker/\n",
    "!sudo mv /var/lib/docker /home/ec2-user/SageMaker/docker\n",
    "!sudo ln -s /home/ec2-user/SageMaker/docker /var/lib/docker\n",
    "!sudo /etc/init.d/docker start"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a8f3054",
   "metadata": {},
   "source": [
    "### 1.2 Dockerfile の作成\n",
    "\n",
    "GPU を利用できるようにするために cuda10.2 を利用できるイメージを使います。また、PIP で paddleOCR を python から実行できるようにライブラリをインストールします。以下のセルを実行すると必要な Dockerfile が ./container に保存されます。\n",
    "\n",
    "- RUN pip3 install paddlepaddle-gpu==2.0.2\n",
    "- RUN pip3 install \"paddleocr>=2.0.1\" "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "09334837",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting ./container/Dockerfile\n"
     ]
    }
   ],
   "source": [
    "%%writefile ./container/Dockerfile\n",
    "# PaddleOCR requires glibc 2.2.3 installed in ubuntu16.04\n",
    "# and cuda10.2 for using GPU\n",
    "FROM nvidia/cuda:10.2-cudnn7-devel-ubuntu16.04\n",
    "    \n",
    "# Set a docker label to advertise multi-model support on the container\n",
    "LABEL com.amazonaws.sagemaker.capabilities.multi-models=true\n",
    "# Set a docker label to enable container to use SAGEMAKER_BIND_TO_PORT environment variable if present\n",
    "LABEL com.amazonaws.sagemaker.capabilities.accept-bind-to-port=true\n",
    "\n",
    "ARG PYTHON_VERSION=3.7.10\n",
    "ARG MMS_VERSION=1.0.8\n",
    "\n",
    "# See http://bugs.python.org/issue19846\n",
    "ENV LANG C.UTF-8\n",
    "ENV LD_LIBRARY_PATH /opt/conda/lib/:$LD_LIBRARY_PATH\n",
    "ENV PATH /opt/conda/bin:$PATH\n",
    "\n",
    "\n",
    "RUN apt-get update && apt-get install -y --no-install-recommends \\\n",
    "    build-essential \\\n",
    "    ca-certificates \\\n",
    "    cmake \\\n",
    "    curl \\\n",
    "    git \\\n",
    "    jq \\\n",
    "    libgl1-mesa-glx \\\n",
    "    libglib2.0-0 \\\n",
    "    libsm6 \\\n",
    "    libxext6 \\\n",
    "    libxrender-dev \\\n",
    "    openjdk-8-jdk-headless \\\n",
    "    vim \\\n",
    "    wget \\\n",
    "    zlib1g-dev\n",
    "\n",
    "RUN curl -L -o ~/miniconda.sh https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh \\\n",
    " && chmod +x ~/miniconda.sh \\\n",
    " && ~/miniconda.sh -b -p /opt/conda \\\n",
    " && rm ~/miniconda.sh \\\n",
    " && /opt/conda/bin/conda update conda \\\n",
    " && /opt/conda/bin/conda install -y \\\n",
    "    python=$PYTHON_VERSION \\\n",
    "    cython==0.29.12 \\\n",
    "    ipython==7.7.0 \\\n",
    "    mkl-include==2019.4 \\\n",
    "    mkl==2019.4 \\\n",
    "    numpy==1.16.4 \\\n",
    "    scipy==1.3.0 \\\n",
    "    typing==3.6.4 \\\n",
    " && /opt/conda/bin/conda clean -ya\n",
    "\n",
    "# install paddleocr\n",
    "RUN pip3 install paddlepaddle-gpu==2.0.2\n",
    "RUN pip3 install \"paddleocr>=2.0.1\" \n",
    "\n",
    "# Install MXNet, MMS, and SageMaker Inference Toolkit to set up MMS\n",
    "RUN pip3 --no-cache-dir install mxnet \\\n",
    "                                multi-model-server \\\n",
    "                                sagemaker-inference \\\n",
    "                                retrying\n",
    "\n",
    "\n",
    "\n",
    "# Copy entrypoint script to the image\n",
    "COPY dockerd-entrypoint.py /usr/local/bin/dockerd-entrypoint.py\n",
    "RUN chmod +x /usr/local/bin/dockerd-entrypoint.py\n",
    "\n",
    "RUN mkdir -p /home/model-server/\n",
    "\n",
    "# Copy the default custom service file to handle incoming data and inference requests\n",
    "COPY model_handler.py /home/model-server/model_handler.py\n",
    "\n",
    "# Define an entrypoint script for the docker image\n",
    "ENTRYPOINT [\"python\", \"/usr/local/bin/dockerd-entrypoint.py\"]\n",
    "\n",
    "# Define command to be passed to the entrypoint\n",
    "CMD [\"serve\"]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52b589c4",
   "metadata": {},
   "source": [
    "### 1.3 dockerd-entrypoint.py の作成\n",
    "\n",
    "ここはサンプルそのままです。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "02bdd19d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting ./container/dockerd-entrypoint.py\n"
     ]
    }
   ],
   "source": [
    "%%writefile ./container/dockerd-entrypoint.py\n",
    "\n",
    "import subprocess\n",
    "import sys\n",
    "import shlex\n",
    "import os\n",
    "from retrying import retry\n",
    "from subprocess import CalledProcessError\n",
    "from sagemaker_inference import model_server\n",
    "\n",
    "def _retry_if_error(exception):\n",
    "    return isinstance(exception, CalledProcessError or OSError)\n",
    "\n",
    "@retry(stop_max_delay=1000 * 50,\n",
    "       retry_on_exception=_retry_if_error)\n",
    "def _start_mms():\n",
    "    # by default the number of workers per model is 1, but we can configure it through the\n",
    "    # environment variable below if desired.\n",
    "    # os.environ['SAGEMAKER_MODEL_SERVER_WORKERS'] = '2'\n",
    "    model_server.start_model_server(handler_service='/home/model-server/model_handler.py:handle')\n",
    "\n",
    "def main():\n",
    "    if sys.argv[1] == 'serve':\n",
    "        _start_mms()\n",
    "    else:\n",
    "        subprocess.check_call(shlex.split(' '.join(sys.argv[1:])))\n",
    "\n",
    "    # prevent docker exit\n",
    "    subprocess.call(['tail', '-f', '/dev/null'])\n",
    "    \n",
    "main()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7110433",
   "metadata": {},
   "source": [
    "### 1.4 model_handler.py の作成\n",
    "\n",
    "\n",
    "実際にモデルで推論する際の挙動を記述します。その挙動は、グローバルの関数の `handle(data, context)` で書かれているように\n",
    "\n",
    "1. 初期化されていなければ initialize で初期化する (モデルをロードするなど）\n",
    "1. データがくればhandleで予測した結果を返す\n",
    "\n",
    "となっています。つまり、initialize と handle を実装すればOKです。initialize は以下のようにモデルをロードする処理を書きます。SageMaker は S3 にモデルをおいておけば、それを /opt/ml/model/ においてくれますので、そこに置かれた各種モデルを読むようにします。S3へのモデル配置はこのあと行います。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "5a422927",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting ./container/model_handler.py\n"
     ]
    }
   ],
   "source": [
    "%%writefile ./container/model_handler.py\n",
    "\n",
    "\"\"\"\n",
    "ModelHandler defines an example model handler for load and inference requests for MXNet CPU models\n",
    "\"\"\"\n",
    "from collections import namedtuple\n",
    "import json\n",
    "import logging\n",
    "import os\n",
    "import re\n",
    "\n",
    "import mxnet as mx\n",
    "import numpy as np\n",
    "from io import BytesIO\n",
    "from paddleocr import PaddleOCR, draw_ocr\n",
    "from glob import glob\n",
    "from PIL import Image\n",
    "import base64\n",
    "\n",
    "class ModelHandler(object):\n",
    "    \"\"\"\n",
    "    A sample Model handler implementation.\n",
    "    \"\"\"\n",
    "\n",
    "    def __init__(self):\n",
    "        self.initialized = False\n",
    "        self.ocr = None\n",
    "\n",
    "    def initialize(self, context):\n",
    "        \"\"\"\n",
    "        Initialize model. This will be called during model loading time\n",
    "        :param context: Initial context contains model server system properties.\n",
    "        :return:\n",
    "        \"\"\"\n",
    "        self.initialized = True\n",
    "        model_dir = \"/opt/ml/model/\"\n",
    "        \n",
    "        # Load ocr model\n",
    "        try:\n",
    "            self.ocr = PaddleOCR(det_model_dir=os.path.join(model_dir,'model/det'),\n",
    "            rec_model_dir=os.path.join(model_dir,'model/rec/ja'),\n",
    "            rec_char_dict_path=os.path.join(model_dir,'model/dict/japan_dict.txt'),\n",
    "            cls_model_dir=os.path.join(model_dir,'model/cls'), \n",
    "            use_angle_cls=True, lang=\"japan\", use_gpu=True)\n",
    "              \n",
    "        except Exception as e:\n",
    "            raise\n",
    "            \n",
    "    def preprocess(self, request):\n",
    "        \"\"\"\n",
    "        Transform raw input into model input data.\n",
    "        :param request: list of raw requests\n",
    "        :return: list of preprocessed model input data\n",
    "        \"\"\"\n",
    "        # Take the input data and pre-process it make it inference ready\n",
    "\n",
    "        img_list = []\n",
    "        for idx, data in enumerate(request):\n",
    "            # Read the bytearray of the image from the input\n",
    "            img_arr = data.get('body')\n",
    "            img_arr = base64.b64decode(img_arr)\n",
    "            img_arr = Image.open(BytesIO(img_arr))\n",
    "            img_arr = np.array(img_arr)\n",
    "            \n",
    "            # Check the number of dimension\n",
    "            assert len(img_arr.shape) == 3, \"Dimension must be 3, but {}\".format(len(img_arr.shape)) \n",
    "\n",
    "            img_list.append(img_arr)\n",
    "\n",
    "        return img_list\n",
    "\n",
    "    def inference(self, model_input):\n",
    "        \"\"\"\n",
    "        Internal inference methods\n",
    "        :param model_input: transformed model input data list\n",
    "        :return: list of inference output \n",
    "        \"\"\"\n",
    "        res_list = []\n",
    "        # Do some inference call to engine here and return output\n",
    "        for img in model_input:\n",
    "            result = self.ocr.ocr(img, cls=True)\n",
    "            for res in result:\n",
    "                ## because float32 is not json serializable, score is converted to float (float64)\n",
    "                ## However the score is in tuple and cannot be replaced. The entire tupple is replaced as list.\n",
    "                string = res[1][0]\n",
    "                score = float(res[1][1])\n",
    "                res[1] = [string,score]\n",
    "\n",
    "            res_list.append(result)\n",
    "        return res_list\n",
    "        \n",
    "    def handle(self, data, context):\n",
    "        \"\"\"\n",
    "        Call preprocess, inference and post-process functions\n",
    "        :param data: input data\n",
    "        :param context: mms context\n",
    "        \"\"\"\n",
    "        \n",
    "        model_input = self.preprocess(data)\n",
    "        model_out = self.inference(model_input)\n",
    "        return model_out\n",
    "\n",
    "_service = ModelHandler()\n",
    "\n",
    "\n",
    "def handle(data, context):\n",
    "    if not _service.initialized:\n",
    "        _service.initialize(context)\n",
    "\n",
    "    if data is None:\n",
    "        return None\n",
    "\n",
    "    return _service.handle(data, context)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40253f0a",
   "metadata": {},
   "source": [
    "### 1.5 コンテナイメージをビルドして ECR に push する\n",
    "\n",
    "ここもサンプルと同じように実行します。`algorithm_name` は好きなものを指定しましょう。  \n",
    "`algorithm_name=paddleocr-gpu`であれば、以下が ECR 上での URI になります。\n",
    "```\n",
    "(アカウントID).dkr.ecr.(リージョン名).amazonaws.com/paddleocr-gpu:latest \n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "085033cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%sh\n",
    "\n",
    "# The name of our algorithm\n",
    "algorithm_name=paddleocr-gpu\n",
    "\n",
    "cd container\n",
    "\n",
    "account=$(aws sts get-caller-identity --query Account --output text)\n",
    "\n",
    "# Get the region defined in the current configuration (default to us-west-2 if none defined)\n",
    "region=$(aws configure get region)\n",
    "region=${region:-us-west-2}\n",
    "\n",
    "fullname=\"${account}.dkr.ecr.${region}.amazonaws.com/${algorithm_name}:latest\"\n",
    "\n",
    "# If the repository doesn't exist in ECR, create it.\n",
    "aws ecr describe-repositories --repository-names \"${algorithm_name}\" > /dev/null 2>&1\n",
    "\n",
    "if [ $? -ne 0 ]\n",
    "then\n",
    "    aws ecr create-repository --repository-name \"${algorithm_name}\" > /dev/null\n",
    "fi\n",
    "\n",
    "# Get the login command from ECR and execute it directly\n",
    "$(aws ecr get-login --region ${region} --no-include-email)\n",
    "\n",
    "docker build -q -t ${algorithm_name} .\n",
    "docker tag ${algorithm_name} ${fullname}\n",
    "\n",
    "docker push ${fullname}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f9e0d1b5",
   "metadata": {},
   "source": [
    "## 1.6 URI のメモ\n",
    "\n",
    "先ほどの命名規則 `(アカウントID).dkr.ecr.(リージョン名).amazonaws.com/paddleocr-gpu:latest` に沿って URI を作成・メモし、後で使えるよう `image_uri` に保存します。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d43beb10",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import boto3\n",
    "\n",
    "account_id = boto3.client('sts').get_caller_identity().get('Account')\n",
    "region = boto3.session.Session().region_name \n",
    "image_uri = str(account_id) + \".dkr.ecr.\" +  region + \".amazonaws.com/paddleocr-gpu:latest\"\n",
    "\n",
    "print(image_uri)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e3753dd2",
   "metadata": {},
   "source": [
    "## 2. コンテナイメージを使って OCR モデルをデプロイ\n",
    "\n",
    "### 2.1. モデルのダウンロード・圧縮・S3へのアップロード\n",
    "\n",
    "\n",
    "PaddleOCR のライブラリは、モデルがローカルにない場合は自動でモデルをダウンロードする仕組みをもっています。しかし今回は、事前にモデルをダウンロードして S3 に保存しておき、デプロイするときは S3 からモデルをダウンロードして利用するようにします。自分で管理するので手間ではありますが、もしライブラリがモデルのダウンロードに失敗しても S3 からダウンロードして対応できます。\n",
    "\n",
    "以下のテキストエリア検出、テキスト認識（認識モデルと日本語辞書）、テキスト分類（角度調整等に利用）の4つのファイルがあり、それぞれダウンロード・解凍して、以下に示すフォルダ構造で保存します。このフォルダ構造は、コンテナイメージをビルドする際に作成した `model_handler.py` の関数 `initialize` でモデルを読み込む際の階層構造と合わせる必要があります。また、モデルの URL は[こちらのファイル](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/paddleocr.py)から確認できます。テキスト認識にかかる2つのファイルは言語固有で、それ以外は、各言語共通のものを使います。\n",
    "\n",
    "以下の階層構造でモデルなどを保存したら、それらを1つに圧縮して `model.tar.gz` にします。これは SageMaker が tar.gz で圧縮されていることを前提とするためです。エンドポイントを作成する際は、この`model.tar.gz`は解凍されて `/opt/ml/model` に展開されます（つまり /opt/ml/model/model/det/ 以下にテキストエリア検出モデルが展開されます）。\n",
    "\n",
    "```\n",
    "model\n",
    "├── det       ... (テキストエリア検出)\n",
    "├── rec\n",
    "│　　 └── ja   ... (テキスト認識モデル)\n",
    "├── dict      ... (日本語辞書)\n",
    "└── cls       ... (テキスト分類)\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0f696264",
   "metadata": {},
   "outputs": [],
   "source": [
    "!mkdir -p model/det\n",
    "!mkdir -p model/rec/ja\n",
    "!mkdir -p model/dict\n",
    "!mkdir -p model/cls\n",
    "\n",
    "!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar -O model/det/en_ppocr_mobile_v2.0_det_infer.tar\n",
    "!cd model/det/ && tar xvf en_ppocr_mobile_v2.0_det_infer.tar --strip-components 1 && rm en_ppocr_mobile_v2.0_det_infer.tar\n",
    "\n",
    "!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar -O model/rec/ja/japan_mobile_v2.0_rec_infer.tar\n",
    "!cd model/rec/ja/ && tar xvf japan_mobile_v2.0_rec_infer.tar --strip-components 1 && rm japan_mobile_v2.0_rec_infer.tar\n",
    "\n",
    "!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar -O model/cls/ch_ppocr_mobile_v2.0_cls_infer.tar\n",
    "!cd model/cls/ && tar xvf ch_ppocr_mobile_v2.0_cls_infer.tar --strip-components 1 && rm ch_ppocr_mobile_v2.0_cls_infer.tar\n",
    "\n",
    "!wget https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/ppocr/utils/dict/japan_dict.txt -O ./model/dict/japan_dict.txt\n",
    "    \n",
    "!tar -zcvf model.tar.gz model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6353187c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sagemaker \n",
    "\n",
    "model_uri = sagemaker.Session().upload_data(\"model.tar.gz\", key_prefix=\"ocr_model\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec8f38a7",
   "metadata": {},
   "source": [
    "### 2.2. デプロイ\n",
    "\n",
    "SageMaker の Model を作成して deploy を実行すればエンドポイントを作成できます。`image_uri`には ECR に push したコンテナイメージの URI を、`model_data` には先ほどアップロードした OCR モデル (model.tar.gz) へのパスを渡します。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "641d56de",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sagemaker.model import Model\n",
    "from sagemaker.predictor import Predictor\n",
    "\n",
    "ocr_model = sagemaker.model.Model(image_uri,\n",
    "                      model_data=model_uri, \n",
    "                      predictor_cls=Predictor,\n",
    "                      role=sagemaker.get_execution_role())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aef14a4a",
   "metadata": {},
   "source": [
    "\n",
    "今回は GPU を使いたいので `ml.g4dn.xlarge` をインスタンスに選んでデプロイします。ただし、これには時間がかかるので、もしデバッグがすんでいなければ、`instance_type=\"local\"`と指定して、ローカル環境でまずはテストしてみましょう。以下でエラーが出る場合は、コンテナイメージに不具合があるはずなので、エラーを CloudWatch Logs で確認して、`Dockerfile` や `model_handler.py` を修正してコンテナイメージをもう一度ビルドします。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c779d41f",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor = ocr_model.deploy(initial_instance_count=1,instance_type=\"ml.g4dn.xlarge\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc22cb1e",
   "metadata": {},
   "source": [
    "### 3. テスト\n",
    "\n",
    "\n",
    "某所から持ってきた画像を試してみます。画像は `model_handler.py` で実装したように base64 でエンコードして送ります。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6f615bc9",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "import base64\n",
    "from io import BytesIO\n",
    "from PIL import Image\n",
    "import PIL\n",
    "\n",
    "image = Image.open(\"test02.png\")\n",
    "if isinstance(image,PIL.PngImagePlugin.PngImageFile):\n",
    "    image = image.convert('RGB') \n",
    "\n",
    "buffered = BytesIO()\n",
    "image.save(buffered, format=\"JPEG\")\n",
    "img_str = base64.b64encode(buffered.getvalue())\n",
    "\n",
    "import json\n",
    "response = json.loads(predictor.predict(img_str))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d22f0ae",
   "metadata": {},
   "source": [
    "\n",
    "\n",
    "`response` には結果が入っていますが、わかりやすくするため、検出された場所に赤枠で囲み、認識されたテキストと対応付けるための通し番号を付けます。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "32a551fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import cv2\n",
    "x_offset = 20\n",
    "y_offset = 0\n",
    "for i, res in enumerate(response):\n",
    "    box = np.reshape(np.array(res[0]), [-1, 1, 2]).astype(np.int64)\n",
    "#     print(box)\n",
    "    image = cv2.putText(np.array(image), '('+str(i)+')', (box[0][0][0] -x_offset, box[0][0][1]-y_offset), \n",
    "                        cv2.FONT_HERSHEY_PLAIN, 1, (255, 0, 0), 1, cv2.LINE_AA)\n",
    "    image = cv2.polylines(np.array(image), [box], True, (255, 0, 0), 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "37714152",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(0): データ転送, (1): 以下の料金は、AmaJnＥC2に「受信 (イン)」/「送信（(アウト)」されるデータ転送量を基にしています。, (2): リージョン;, (3): 米国東部 (オハイオ）・, (4): 料金, (5): イソターネットから （ma0nEC2へのデータ転送 (イン), (6): すべてのデータ受信, (7): O 0OUSD/GB, (8): Amá20nEC2からインターネットへのデータ転送(アウト), (9): 1GB/月まで, (10): 000USD/CB, (11): 次の９,9991B/月, (12): O 09USD/GB, (13): 次の401B/月, (14):  0 085USD/GB, (15): 次の100TB/月, (16): O 07USD/GB, (17): 1501B/月以上, (18): 0 05USD/GB, "
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x800 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "for i,res in enumerate(response):\n",
    "    print('('+str(i)+'): '+res[1][0], end=', ')\n",
    "fig = plt.figure(dpi=200)\n",
    "plt.imshow(image)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6194cdb",
   "metadata": {},
   "source": [
    "## 4. 後片付け\n",
    "\n",
    "最後に不要なエンドポイントを削除しましょう。\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "e234fdd5",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.delete_endpoint()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "59c9914a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}